|Publication number||US7523275 B2|
|Application number||US 10/410,757|
|Publication date||Apr 21, 2009|
|Filing date||Apr 10, 2003|
|Priority date||Apr 10, 2003|
|Also published as||US20040205312|
|Publication number||10410757, 410757, US 7523275 B2, US 7523275B2, US-B2-7523275, US7523275 B2, US7523275B2|
|Inventors||Aviad Zlotnick, Shachar Fienblit, Olympia Gluck, Michael E. Factor, William Frank Micka, Gail Andrea Spear, Smith Hyde II Joseph, Martin Jacob Tross|
|Original Assignee||International Business Machines Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (11), Non-Patent Citations (1), Referenced by (1), Classifications (11), Legal Events (4)|
|External Links: USPTO, USPTO Assignment, Espacenet|
1. Field of the Invention
The present invention relates to a method, system and program for maintaining a copy relationship between primary volumes and corresponding secondary volumes.
2. Description of the Related Art
Data storage systems may maintain a secondary copy of data at a remote site to use in the event of a failure at the primary site. Such dual or shadow copies are typically made as the application system is writing new data to a primary storage device. International Business Machines Corporation (IBM®), the assignee of the subject patent application, provides two systems for maintaining remote copies of data at a secondary site, extended remote copy (XRC) and peer-to-peer remote copy (PPRC). These systems provide a method for recovering data updates between a last, safe backup and a system failure. Such data shadowing systems can also provide an additional remote copy for non-recovery purposes, such as local access at a remote site. These IBM XRC and PPRC systems are described in IBM publication “Remote Copy: Administrator's Guide and Reference,” IBM document no. SC35-0169-02 (IBM Copyright 1994, 1996), which publication is incorporated herein by reference in its entirety.
In such backup systems, data is maintained in volume pairs. A volume pair is comprised of a volume in a primary storage device and a corresponding volume in a secondary storage device that includes an identical copy of the data maintained in the primary volume. Typically, the primary volume of the pair will be maintained in a primary direct access storage device (DASD) and the secondary volume of the pair is maintained in a secondary DASD shadowing the data on the primary DASD. A primary storage controller may be provided to control access to the primary storage and a secondary storage controller may be provided to control access to the secondary storage.
In PPRC mirroring, when establishing a remote copy relationship between data sets in the primary volumes and secondary volumes, an initial copy of the primary volumes is written to the secondary volumes in the secondary DASD. Data sets from the primary volume are copied asynchronously during the initial copy, which means that the write acknowledgment is returned immediately to the host even before the data is physically copied to the secondary DASD over a dedicated cable or line. The initial copy operation sends the data sets in the PPRC relationship over the link in groups of data sets, referred to as establish chains.
In one mode of PPRC, any host writes to data sets in the primary volumes in the PPRC relationship while the initial copy operation is pending are intercepted. The initial copy logs the write operation and after completing the initial copy of a group of data sets, the logged writes are then transmitted over the line to the secondary site. If the initial copy operation has completed with respect to the data set of the intercepted write, then the data sets are copied synchronously to the corresponding secondary volume(s) in the secondary DASD, which means that acknowledgment of the write is not returned to the host initiating the write until the write completes at the secondary site, and acknowledgment is returned to the primary site to return to the host. Host operations may be delayed pending receipt of the synchronous acknowledgment.
The intercepted target data sets that are written synchronously to the secondary site have to share a link with the group of data being copied asynchronously, including both initial copy data and write requests that are handled asynchronously. This sharing of the link can cause further delays in processing the intercepted synchronous writes because the typically large size of asynchronous writes consumes a substantial amount of bandwidth, thereby causing delays in transmitting and processing the intercepted host writes being handled synchronously.
For these reasons, there is a need in the art to provide improved techniques for transferring data in primary volumes being mirrored at a remote site.
Provided are a method, system, and program for accessing a resource. Requests are generated to access a resource in a first access mode and a second access mode. The requests are processed to access the resource in the second mode before processing at least one request to access the resource in the first access mode. The processing of the requests to access the resource in the first access mode is delayed for a time period after processing all the requests to access the resource in the second access mode in order to wait to receive a subsequent request to access the resource in the second access mode.
Further provided are a method, system, and program for maintaining a copy relationship between at least one primary volume and at least one corresponding secondary volume, wherein data in the at least one primary volume in the copy relationship is copied to the corresponding at least one secondary volume in the copy relationship. Writes are generated comprising data in the at least one primary volume to copy to the corresponding at least one secondary volume in the copy relationship in a first write mode and writes are generated comprising write requests to the at least one primary volume in the copy relationship to copy to at least one corresponding secondary volume in a second write mode. A plurality of the writes are transferred to the at least one secondary volume in the second write mode before processing at least one write to the secondary volume in the first mode. The processing of writes to the at least one secondary volume in the first write mode is delayed for a time period after processing all the writes to the at least one secondary volume in the second write mode in order to wait to receive a subsequent write to one primary volume in the copy relationship in the second write mode.
In further implementations, the writes in the first write mode may include data being copied from the at least one primary volume in the copy relationship to the corresponding at least one secondary volume as part of an initial copy operation to copy all the data in the at least one primary volume in the copy relationship to the at least one corresponding secondary volume.
In yet further implementations, the writes in the first write mode may further include writes to the at least one primary volume received after initiating the initial copy operation.
Still further, the first write mode comprises an asynchronous write mode and the second write mode comprises a synchronous write mode.
Described implementations provide techniques for allowing certain types of requests, such as high priority requests, to be processed without being continually delayed by other types of write requests, such as lower priority requests that may consume substantial resources.
Referring now to the drawings in which like reference numbers represent corresponding parts throughout:
In the following description, reference is made to the accompanying drawings which form a part hereof and which illustrate several implementations of the present invention. It is understood that other implementations may be utilized and structural and operational changes may be made without departing from the scope of the present invention.
A primary storage manager 22 performs data management operations at the primary controller 6 and a secondary storage manager 24 performs data management operations at the secondary controller 16.
The primary 6 and secondary 16 controllers may comprise any storage management system known in the art, such as a storage controller, server, enterprise storage server, etc. The primary 4 and secondary 14 storages may comprise any storage system known in the art, such as a Direct Access Storage Device (DASD), Just a Bunch of Disks (JBOD), a Redundant Array of Independent Disks (RAID), virtualization device, tape storage, optical disk storage, or any other storage system known in the art.
In certain implementations, the primary 8 and secondary 18 sites may be implemented in different power boundaries, such that the destruction or substantial failure at one site will not impact the data stored at the other sites. Further, the primary 8 and secondary 18 sites may be in different geographical locations, in a same building, but different floors or rooms, in different buildings in a same geographical locations, or separated by a distance.
The primary controller 6 further includes a memory 26, which may comprise any volatile or non-volatile memory or storage device known in the art, that maintains the following information, which may be maintained in any data structure format known in the art:
The write counter 48 (
If (at block 214) the high priority queue 30 is empty, then the primary storage manager 22 sets (at block 216) the delay timer 50 (
With the described logic, even after the high priority queue 30 empties, the primary storage manager 22 delays the length of the delay time 34 before copying an asynchronous write to the secondary storage 14, which may comprise the write of an establish chain or a host write request to which asynchronous acknowledgment was returned. This allows write requests to be synchronously processed without being continually delayed by the copying of a larger asynchronous write to the secondary volumes 12 in the copy relationship. The described implementations further allow the synchronous writes to be processed without having to wait for link resources that are being used by lower priority asynchronous write requests, such as establish chains or host write requests handled asynchronously, but only with other synchronous writes being transferred, such as writes to primary volumes in a copy relationship that have been copied to the secondary volume 12 as part of the initial copy operation.
In certain implementations, the delay time 34 and number of synchronous writes to process 32 parameters may be set to empirically determined optimal values to increase the speed of processing synchronous host write requests and avoid any undue delays to the host, and at the same time continue with the copying of asynchronous writes to the secondary volumes 12. The delay time 34 and number of writes 32 can be set manually by an administrator or dynamically during operations based on the system performance. For instance, in certain implementations the delay time 34 can be set to a value approximately, but slightly more, than the average time between the arrival of synchronous host write requests to provide sufficient time to likely capture a host write request before proceeding with the copying of the lower priority asynchronous writes to the secondary storage 14. Still further, one may want to set the delay time 34 close to the average arrival time between the synchronous host write requests, but not more than approximately half the average time for an asynchronous write to complete in order to avoid a delay during which an entire asynchronous write could have been completed. Thus, the average time between host write requests and the average time to complete an asynchronous write can be used to determine an optimal delay time 34.
The data management techniques disclosed herein may be implemented as a method, apparatus or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof. The term “article of manufacture” as used herein refers to code or logic implemented in hardware logic (e.g., an integrated circuit chip, Programmable Gate Array (PGA), Application Specific Integrated Circuit (ASIC), etc.) or a computer readable medium (e.g., magnetic storage medium (e.g., hard disk drives, floppy disks,, tape, etc.), optical storage (CD-ROMs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, PAMs, DRAMs, SRAMs, firmware, programmable logic, etc.). Code in the computer readable medium is accessed and executed by a processor. The code may further be accessible through a transmission media or from a file server over a network. In such cases, the article of manufacture in which the code is implemented may comprise a transmission media, such as a network transmission line, wireless transmission media, signals propagating through space, radio waves, infrared signals, etc. Of course, those skilled in the art will recognize that many modifications may be made to this configuration without departing from the scope of the present invention, and that the article of manufacture may comprise any information bearing medium known in the art.
In certain implementations, the primary controller 6 handles synchronously host writes to primary volumes already copied over as part of the initial copy operation and handles asynchronously host writes to primary volumes not yet copied to the secondary storage 14 by the initial copy procedure. Further, initial copy operations are handled asynchronously. In alternative implementations, different data transfer modes, asynchronous versus synchronous, may be used to handle host writes and initial copy data than that described herein.
In described implementations, asynchronous host writes and initial copy writes to the secondary storage 12 are queued in the same low priority queue 28. In the low priority queue 28, the asynchronous host writes may be processed after the initial copy writes or between initial copy writes. In alternative implementations, different queues may be used for the asynchronous host writes and initial copy writes.
In the described implementations, the primary volumes and secondary volumes are in different, remote storage systems at different sites 8, 18. In alternative implementations, the primary and secondary volumes may be in the same storage device or system.
The logic of
The foregoing description of the implementations has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the invention be limited not by this detailed description, but rather by the claims appended hereto. The above specification, examples and data provide a complete description of the manufacture and use of the composition of the invention. Since many implementations of the invention can be made without departing from the spirit and scope of the invention, the invention resides in the claims hereinafter appended.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US5530871||Aug 23, 1994||Jun 25, 1996||Nec Corporation||Asynchronous input and output control system|
|US5592685||Oct 7, 1992||Jan 7, 1997||Digital Equipment Corporation||Synchronous/asynchronous partitioning of an asynchronous bus interface|
|US5623599||Jul 29, 1994||Apr 22, 1997||International Business Machines Corporation||Method and apparatus for processing a synchronizing marker for an asynchronous remote data copy|
|US5913215 *||Feb 19, 1997||Jun 15, 1999||Seymour I. Rubinstein||Browse by prompted keyword phrases with an improved method for obtaining an initial document set|
|US6098122||Mar 27, 1998||Aug 1, 2000||International Business Machines Corporation||Method and apparatus for adaptively blocking outgoing communication requests and adjusting the blocking factor according to the volume of requests being received in an information handling system|
|US6173377 *||Apr 17, 1998||Jan 9, 2001||Emc Corporation||Remote data mirroring|
|US6237008||Jul 20, 1998||May 22, 2001||International Business Machines Corporation||System and method for enabling pair-pair remote copy storage volumes to mirror data in another storage volume|
|US6496908 *||May 18, 2001||Dec 17, 2002||Emc Corporation||Remote mirroring|
|US6684306 *||Jul 14, 2000||Jan 27, 2004||Hitachi, Ltd.||Data backup in presence of pending hazard|
|JPH03282756A||Title not available|
|JPH04273323A||Title not available|
|1||*||Iyer, Sitaram and Druschel, Peter. "Anticipatory scheduling: A disk scheduling framework to overcome deceptive idleness in synchronous I/O." Aug. 24, 2001. as accessed at <http://www.cs.rice.edu/~ssiyer/r/antsched/> on Dec. 4, 2008.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US8261029 *||Mar 28, 2007||Sep 4, 2012||Emc Corporation||Dynamic balancing of writes between multiple storage devices|
|U.S. Classification||711/162, 711/161, 711/154|
|International Classification||G06F12/00, G06F11/20|
|Cooperative Classification||G06F11/2074, G06F11/2069, G06F11/2076, G06F11/2071|
|European Classification||G06F11/20S2M, G06F11/20S2P|
|Apr 10, 2003||AS||Assignment|
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:ZLOTNICK, AVIAD;FIENBLIT, SHACHAR;GLUCK, OLYMPIA;AND OTHERS;REEL/FRAME:013968/0373;SIGNING DATES FROM 20030323 TO 20030408
|Dec 3, 2012||REMI||Maintenance fee reminder mailed|
|Apr 18, 2013||FPAY||Fee payment|
Year of fee payment: 4
|Apr 18, 2013||SULP||Surcharge for late payment|